AutoGNR combines non-recursive, per-hop and per-type aggregation with differentiable architecture search to automatically select useful node type combinations for heterogeneous graph classification.
Distance encoding: Design provably more powerful neural networks for graph rep- resentation learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Automated Heterogeneous Network learning with Non-Recursive Message Passing
AutoGNR combines non-recursive, per-hop and per-type aggregation with differentiable architecture search to automatically select useful node type combinations for heterogeneous graph classification.